Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    theory suggests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oload
    0.60
    ampilkan
    0.58
     ರೆ
    0.57
     모습을
    0.55
     ぞ
    0.55
    isLen
    0.55
    ddots
    0.54
     സമൂ
    0.53
    rake
    0.53
    mailto
    0.52
    POSITIVE LOGITS
     suggests
    2.31
     suggest
    2.28
     suggested
    2.13
     argues
    2.06
     argue
    1.98
     believes
    1.92
     argued
    1.90
     believe
    1.88
    suggest
    1.87
     Suggest
    1.87
    Act Density 0.467%

    No Known Activations